Toward a Universal Map of EEG: A Semantic, Low-Dimensional Manifold for EEG Classification, Clustering, and Prognostication.

Journal: Annals of neurology
Published Date:

Abstract

OBJECTIVE: Prognostication in patients with disorders of consciousness (DOCs) remains challenging because of heterogeneous etiologies, pathophysiologies and, consequently, highly variable electroencephalograms (EEGs). Here, we use EEG patterns that are well-characterizable to create a latent map that positions novel EEGs along a continuum. We asses this map as a generalizable tool to extract prognostically valuable information from long-term EEG, by predicting outcome post-cardiac arrest as a first use case.

Authors

  • Laura Krumm
    Computational Neurology, Department of Neurology and Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Dominik D Kranz
    Computational Neurology, Department of Neurology and Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Mustafa Halimeh
    Computational Neurology, Department of Neurology and Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Alexander Nelde
    Computational Neurology, Department of Neurology and Berlin Institute of Health, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Edilberto Amorim
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA. Electronic address: edilbertoamorim@gmail.com.
  • Sahar Zafar
    Department of Neurology, Massachusetts General Hospital, Boston, MA, United States.
  • Jin Jing
    Department of Neurology, Massachusetts General Hospital, Boston, MA, USA.
  • Robert J Thomas
    Division of Pulmonary, Critical Care & Sleep, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA.
  • M Brandon Westover
    Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts.
  • Christian Meisel
    Technical University of Dresden, 01069 Dresden, Germany; Boston Children's Hospital, Boston, USA. Electronic address: christian@meisel.de.